© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206268
    Prev
    Next
    INDEX
    Explanations

    punctuation and code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    1.10
    ג
    1.10
    وك
    1.09
    <0x80>
    1.07
    ม
    1.02
    د
    1.02
    д
    0.99
    ادث
    0.89
    ד
    0.88
     =
    0.87
    POSITIVE LOGITS
    as
    1.64
    an
    1.52
    on
    1.37
    at
    1.25
    p
    1.25
    is
    1.16
    ie
    1.13
    lg
    1.05
    law
    1.05
    las
    1.05
    Activations Density 0.000%

    No Known Activations